Curricula Vitae

Education

PhD Genetics, Bioinformatics, and Computational Biology Virginia Tech: 2011
Bachelor of Science in Computer Science University of Illinois Springfield: 2005

Adjunct Faculty of Computer Science University of the Cumberlands: 2023 – Present
Faculty of Computer Science BYU-Idaho: 2020 – 2021
Assistant Professor of Computer Science Southern Virginia University: 2017 – 2018
Visiting Faculty of Computer Science BYU-Idaho: 2015 – 2017
CS/EE Adjunct BYU-Idaho: 2014 – 2015
Bioinformatician EMBL–European Bioinformatics Institute: 2012 – 2014
Bioinformatics Research Assistant, Tyler Lab Virginia Bioinformatics Institute: 2006 – 2011

Ensembl Genomes 2016: more genomes, more complexity. Kersey, Paul; et al. – Nucl. Acids Res. (04 January 2016) 44 (D1): D574-D580
Ensembl Genomes 2013: Scaling up access to genome-wide data. Kersey, Paul; et al. – Nucl. Acids Res. (1 January 2014) 42 (D1): D546-D552
Using Interpolation to Estimate System Uncertainty in Gene Expression Experiments. Falin LJ, Tyler BM (2011) – PLoS ONE 6(7): e22071.
Systems Uncertainty in Systems Biology & Gene Function Prediction Falin LJ (2011) – PhD Dissertation
Adapting Teaching to the Needs of the Learner VT Hokie Stone Commemoration – 2010
System Uncertainty in Gene Expression Data VT Graduate Research Symposium – 2010
Microarray Data Inference ACC Interdisciplinary Forum for Discovery in the Life Sciences – 2010
Microarray Data Inference ISCB Intelligent Systems for Molecular Biology – 2010
OpenCL – Now everyone has a super computer (almost) Virginia Bioinformatics Institute – 2009
Inference of Functional Modules in Regulatory Networks Virginia Bioinformatics Institute – 2007

Aug 2022 – Mar 2023

Led a team of data scientists developing and deploying machine learning models for financial fraud detection by multinational banks and credit unions.
Worked with in-house AWS Cloud Architects to develop least-privilege IAM role architectures and RBAC policy frameworks in AWS to enable secure data sharing with remote clients via cross-account roles.
Developed SOP guidelines to ensure adherence to GDPR and other multinational data security and privacy regulations.
Increased project scheduling capacity by over 50% through cross training an underutilized team.
Redesigned data scientist onboarding and training materials to reduce onboard time from 5 to 3 months.
Created project management procedures to enforce data provenance and streamline transferring projects between divisions.

Aug 2019 – Jul 2020

Developed an ML-powered, automatic shift scheduling SaaS product using React, NodeJS, and Firebase.
Built Bash and Python scripts to automate deployment to Heroku.
Integrated with Stripe payment APIs for subscription-based payments.
Wrote technical documentation, user onboarding guides, and other customer support materials.

May 2017 – Jul 2019

Used the CRISP-DM process model to develop custom heuristic algorithms and statistical methods to help clients solve data analysis, data visualization, and other machine learning problems, using a mix of custom algorithms and off-the-shelf libraries, including pandas, NumPy, matplotlib, scikit-learn, TensorFlow, and keras.
Used Python to create a custom data processing and machine learning pipeline for a CAD software company to allow for enhanced metadata recognition and textual analysis.
Wrote process reports and technical whitepapers for stakeholders of mixed technical backgrounds.

Jul 2012 – April 2014

Worked with international collaborators to help add over 30,000 genomic datasets to a bioinformatics SaaS research tool accessed by tens of thousands of users.
Developed custom map-reduce algorithms in Perl and Python to efficiently process proteomics and metabolomics data using Platform LSF pipelines.
Developed REST APIs used by thousands of researchers, accessing data from multiple datastores, including MySQL, Oracle, Neo4J, and MongoDB.
Developed ML algorithms and data pipelines for genomic data processing, protein function prediction, and metabolomic network inference.
Wrote training and project updated presentations and whitepapers, contributed to internal documentation and team publications.

Jan 2006 – May 2011

Reduced microarray analysis costs by implementing novel statistical methods for quantifying uncertainty in sample data using C and the GNU Scientific Library.
Developed an oomycete genome browser using Perl visualization and analysis scripts.
Developed microarray data processing pipelines in Python, R, Perl, and C.
Developed training materials, taught ad-hoc and formal undergraduate classes and training cohorts.